Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 298  43 335  69 539 611   6 579  71 260  51 749 662 737 104 910 969 897 218 222
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 298 222 260 218 897 662 749  NA  NA 910 335  NA 737 969  51 539  69 104  43   6  71 579 611
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 2 3 5 3 1 2 4 4 2 5
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y"
[26] "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y"
[26] "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "r" "h" "z" "j" "o" "W" "E" "M" "D" "C"

Are all/any elements TRUE

  • Input: logical vector
  • Output: single logical value
  • Task: try, understand what happens when you use manyNumbersWithNA instead of manyNumbers.
all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1] 16 17
which( manyNumbersWithNA > 900 )
[1] 10 14
which( is.na( manyNumbersWithNA ) )
[1]  8  9 12

Filtering vector elements

  • Input: any vector and filtering condition
  • Output: elements of the input vector
  • Note: several ways to get the same effect
manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 910 969
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 910 969
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 910 969

Are some elements among other elements

  • Input: two vectors
  • Output: a logical vector corresponding to the first input vector
"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "W" "E" "M" "D" "C"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "r" "h" "z" "j" "o"
manyNumbers %in% 300:600
 [1] FALSE FALSE  TRUE FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[18] FALSE FALSE FALSE
which( manyNumbers %in% 300:600 )
[1] 3 5 8
sum( manyNumbers %in% 300:600 )
[1] 3

Pick one of two (three) depending on condition

  • Input: a logical vector and two vectors additional vectors (for TRUE, for FALSE)
  • Output: elements of the additional vectors
  • Note: it can take care of NAs
if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" "small" "small" "small" "large" "large" "large" NA      NA      "large" "small" NA     
[13] "large" "large" "small" "large" "small" "small" "small" "small" "small" "large" "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "small"   "small"   "small"   "large"   "large"   "large"   "UNKNOWN" "UNKNOWN" "large"  
[11] "small"   "UNKNOWN" "large"   "large"   "small"   "large"   "small"   "small"   "small"   "small"  
[21] "small"   "large"   "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0   0   0   0 897 662 749  NA  NA 910   0  NA 737 969   0 539   0   0   0   0   0 579 611

Duplicates and unique elements

  • Input: a vector
unique( duplicatedNumbers )
[1] 2 3 5 1 4
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  2  3  5  1  4
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE  TRUE FALSE  TRUE FALSE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 14
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 969
which.min( manyNumbersWithNA )
[1] 20
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 6
range( manyNumbersWithNA, na.rm = TRUE )
[1]   6 969

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 298 222 260 218 897 662 749  NA  NA 910 335  NA 737 969  51 539  69 104  43   6  71 579 611
sort( manyNumbersWithNA )
 [1]   6  43  51  69  71 104 218 222 260 298 335 539 579 611 662 737 749 897 910 969
sort( manyNumbersWithNA, na.last = TRUE )
 [1]   6  43  51  69  71 104 218 222 260 298 335 539 579 611 662 737 749 897 910 969  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 969 910 897 749 737 662 611 579 539 335 298 260 222 218 104  71  69  51  43   6  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 298 222 260 218 897
order( manyNumbersWithNA[1:5] )
[1] 4 2 3 1 5
rank( manyNumbersWithNA[1:5] )
[1] 4 2 3 1 5
sort( mixedLetters )
 [1] "C" "D" "E" "h" "j" "M" "o" "r" "W" "z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 7.0 4.5 4.5 1.0 9.5 2.5 2.5 7.0 9.5 7.0
rank( manyDuplicates, ties.method = "min" )
 [1] 6 4 4 1 9 2 2 6 9 6
rank( manyDuplicates, ties.method = "random" )
 [1]  7  5  4  1 10  2  3  8  9  6

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.0000000 -0.5000000  0.0000000  0.5000000  1.0000000 -0.7318272  0.1974809 -0.2113121 -0.2351181
[10] -0.8045286 -1.7357114 -1.7574160  1.6503601  1.6069962 -0.8519964
round( v, 0 )
 [1] -1  0  0  0  1 -1  0  0  0 -1 -2 -2  2  2 -1
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -0.7  0.2 -0.2 -0.2 -0.8 -1.7 -1.8  1.7  1.6 -0.9
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -0.73  0.20 -0.21 -0.24 -0.80 -1.74 -1.76  1.65  1.61 -0.85
floor( v )
 [1] -1 -1  0  0  1 -1  0 -1 -1 -1 -2 -2  1  1 -1
ceiling( v )
 [1] -1  0  0  1  1  0  1  0  0  0 -1 -1  2  2  0

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 x 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC